KR101033385B1 - Method and apparatus for diagnosing troubles of individuals with developmental disabilities based on functional near infrared spectroscopy - Google Patents

Abstract

PURPOSE: A method and apparatus for diagnosing troubles of individuals with developmental disabilities based on functional near infrared spectroscopy are provided to extract characteristic data using diagnosing troubles by collecting fNIRS data from everyday life. CONSTITUTION: An apparatus for diagnosing troubles of individuals with developmental disabilities is comprised of a data collection unit(110), a preprocessing unit(120), a characteristics extracting unit(130), a trouble diagnosis part, a general person database(150), and a trouble diagnosis reference database(160). The data collection unit collects fNIRS(Functional Near Infrared Spectroscopy) data from a subject. A stimulus program used for analyzing the function of a brain includes a block design protocol, a continuous protocol, and an ERP(Event-Related Potential) protocol. The data collection unit collects the fNIRS data through a transmitter and receiver which are attached to the brain of the subject.

Description

METHOD AND APPARATUS FOR diagnosing troubles OF Individuals with Developmental Disabilities BASED ON FUNCTIONAL NEAR INFRARED SPECTROSCOPY}

One embodiment of the present invention relates to a method and apparatus for diagnosing a disorder of a fNIRS-based developmental disorder.

In recent years, social functions have developed, and the number of people with social developmental disabilities tends to increase due to changes in the surrounding environment. People with this tendency have different brain functions from those of ordinary people, and since they are divided into various classes, it is necessary to have a diagnosis technique for what disorders they have.

However, according to the diagnosis of developmental disposition propensity, play therapy using mediators has been widely used in the humanities / private series, but there is a limit to suggesting an appropriate approach because it does not provide objective evidence of disability judgment.

On the other hand, EEG, fMRI, etc. have been widely used for diagnosing disorders for people with developmental disabilities. EEG (Electroencephalogram) has the advantage that can be measured continuously in everyday life, but there is a problem that the accuracy of the brain function analysis due to a lot of signal noise. In addition, fMRI (functional Magnetic Resonance Imaging) is the most frequently used device for brain function analysis, but there is a problem that can not measure the information during the expensive and developmental life for the disabled.

One embodiment of the present invention is easy to wear for analyzing the brain function, and provides a method and apparatus for diagnosing disorders of fNIRS-based developmental disorders that can measure brain function in real time even in daily life.

Disability diagnosis apparatus according to an embodiment of the present invention is a data collection unit for collecting fNIRS data from a subject, a feature extraction unit for extracting the characteristic data using the collected fNIRS data, and using the extracted characteristic data A disorder diagnosis section that categorizes the disorder diagnosis for the subject.

In this case, the data collection unit may collect the fNIRS data through the transmitter and the receiver attached to the location of the brain function measurement of the subject.

In this case, the data collector may collect the fNIRS data from the subject using any one of a block design protocol, a continuous protocol, and an ERP protocol as a stimulus program used for brain function analysis.

In addition, the apparatus for diagnosing the disorder further includes a preprocessor configured to acquire signal data by analyzing the collected fNIRS data. In this case, the feature extractor is a Fourier transform theory including a Fast Fourier Transform (FFT) and a Short-time Fourier Transform (STFT), Daubechies, Biorthogonal, and Mexican for the obtained target data. Characteristic data can be extracted using either the WAVELETS theory, which includes Hat, or the Continuous Wavelet Transform (CWT) theory.

At this time, the failure diagnosis unit based on the extracted characteristic data evolution computing such as neural network (ANN) theory, Bayesian theory, hidden Markov model (HMM) theory or genetic algorithm (GA), ant colonization system (ACS) Evolutionary Computing Theories can be used to classify the disorder diagnosis for the subject.

In this case, the disability diagnosis unit may classify the disability diagnosis associated with any one of the cognitive function, language function, social performance function, exercise ability function, daily living function for the subject.

The apparatus for diagnosing the disorder further includes a general public database storing general fNIRS data, and a failure criteria database storing failure reference data. In this case, the disability diagnosis unit may classify the disability diagnosis for the subject by comparing the extracted characteristic data with the general fNIRS data or the disability reference data.

Disability diagnosis method according to an embodiment of the present invention comprises the steps of collecting the fNIRS data from the subject, extracting the characteristic data using the collected fNIRS data, and the disorder for the subject using the extracted characteristic data Classifying the diagnosis.

According to an embodiment of the present invention, the fNIRS data can be used to present more objective results than the disability diagnosis method for the existing developmental disorder, and fNIRS data can be collected during daily life to extract characteristic data for use in diagnosing the disorder. Can be.

According to an embodiment of the present invention, if the apparatus for diagnosing a disorder is miniaturized or portable, the apparatus may be used for education for a developmentally disabled person who has a growing trend in society.

Hereinafter, various embodiments of the present invention will be described in detail with reference to the accompanying drawings and accompanying drawings, but the present invention is not limited to or limited by the embodiments.

1 is a diagram showing the configuration of a failure diagnosis apparatus according to an embodiment of the present invention.

Referring to FIG. 1, the failure diagnosis apparatus 100 may include a data collector 110, a preprocessor 120, a feature extractor 130, a failure diagnosis unit 140, a public database 150, and a failure reference database ( 160).

The data collector 110 collects fNIRS data from the subject. Here, the subject is a developmental disorder, and fNIRS (FUNCTIONAL NEAR INFRARED SPECTROSCOPY) data refers to data used for brain function analysis.

In an embodiment, the data collection unit 110 may collect the fNIRS data using a stimulus program used for brain function analysis. The stimulus program may include a block-design protocol, a continuous protocol, and an event-related potential protocol.

In addition, the data collection unit 110 may collect the fNIRS data through a transmitter and a receiver attached to the subject's brain function measurement position.

2 is a diagram illustrating an example of attaching a transmitter and a receiver to a brain function measurement position according to an embodiment of the present invention.

Referring to FIG. 2, a manager performing a disability diagnosis attaches a transmitter and a receiver to the brain skin of a subject. The transmitter and the receiver may be attached to a predetermined brain function measurement position. The transmitter is a transmitter that transmits a signal to the subject for the fNIRS data collection. A receiver is a receiver and receives a response signal to a signal transmitted through a transmitter. Accordingly, the data collector 110 may collect the response signal received through the receiver as fNIRS data.

The preprocessor 120 preprocesses the collected fNIRS data. For example, the preprocessor 120 may perform preprocessing for brain function analysis based on the fNIRS data or data collected in real time. Here, the preprocessing operation may be selected depending on the protocol, and performs a function of acquiring the target data for brain function analysis.

The feature extractor 130 extracts feature data using the preprocessed fNIRS data. Here, the feature extractor 130 uses Fourier transform theory such as Fast Fourier Transform (FFT), Short-time Fourier Transform (STFT), Daubechies, Biorthogonal, The characteristic data may be extracted using a wavelet (TSWLETS) theory, a continuous wavelet transform (CWT) theory, such as Mexican Hat, or a new algorithm theory.

The disability diagnosis unit 140 may classify the disability diagnosis for the subject by using the extracted characteristic data.

In an embodiment, the failure diagnosis unit 140 may include an artificial neural network (ANN) theory, a bayesian theory, and a hidden markov-chain model (HMM) theory based on the extracted characteristic data. In addition, the diagnosis of the disorder of the subject may be classified using any one of the theory of evolutionary computing, including genetic algorithm (GA) and ant colony system (ACS).

Here, in order to classify the diagnosis of the disorder, the disability reference data of the position where the brain function analysis is to be used is used. For this purpose, the public database 150 and the disability reference database 160 are required. The public database 150 stores general fNIRS data for the general public. In addition, the disability criterion database 160 stores the disability criterion data as preliminary data used for determining a conventional developmental disability.

In this case, the disability diagnosis unit 140 may classify the disability diagnosis for the subject by comparing the extracted characteristic data with the general fNIRS data or the disability reference data.

The disability diagnosis unit 140 may classify the disability diagnosis into any one of a cognitive function, a language function, a social function function, an exercise ability function, and a daily living function. The failure diagnosis unit 140 may primarily classify the functions into a failure diagnosis, and expand the detailed failure diagnosis name in the form of a tree conceptual subordinate node for each failure of each function.

3 is a diagram illustrating an example of comparing the brain of a general person with a developmental disability according to an embodiment of the present invention.

Referring to FIG. 3, for a specific brain stimulation program, the general person 310 and the person with developmental disability 320 perform different brain parts.

That is, the average person 310 on average for a specific brain function stimulus shows that the functions are activated for each brain region. That is, in the drawings, portions treated with different shapes (one line hatch, two line hatches, thick dots, and small dots) may be regarded as performing different functions for each brain region. For example, the hatched portion can be seen as the most active brain function.

However, in the case of a developmental disability 320, the function of each brain region is not activated. That is, in the drawing, the brain region is represented by the same part (small point) in the mode, which can be seen that the brain region performs only the same function of one or two kinds.

Therefore, the apparatus 100 for diagnosing the disorder of the present invention may perform accurate diagnosis of the disorder by finally performing difference analysis or classifying them using fNIRS data according to the brain stimulation program.

4 is a flowchart illustrating an example of a failure diagnosis method according to an embodiment of the present invention.

The failure diagnosis method collects fNIRS data through a transmitter and a receiver attached to the subject (410). The transmitter and the receiver may be attached to a predetermined brain function measurement position. In this case, the disorder diagnosis method is a stimulus program used for brain function analysis, and may collect the fNIRS data from the subject using any one of a block design protocol, a continuous protocol, and an ERP protocol.

The fault diagnosis method preprocesses the collected fNIRS data (420). In this case, the method for diagnosing a disorder may obtain target data by performing preprocessing for brain function analysis based on the collected fNIRS data or data collected in real time.

The fault diagnosis method extracts characteristic data using the preprocessed fNIRS data (430). In this case, the method for diagnosing a disorder may use any one of a fast Fourier transform, a Fourier transform theory including a short time Fourier transform, a wavelet theory including Daubechies, Biorthogonal, Mexican Hat, or a continuous wavelet transform theory related to the acquired target data. Characteristic data can be extracted.

The method for diagnosing a disorder classifies the disorder diagnosis for the subject using the extracted characteristic data (440). At this time, the method for diagnosing the disorder is based on the extracted characteristic data, the neural network theory, Bayesian theory, hidden Markov model theory, or genetic algorithm, the evolutionary computing theory including the ant colonization system using any one of the subjects Disability diagnosis can be classified. Here, the disorder diagnosis may be related to any one of cognitive function, language function, social function function, motor function function, and daily living function.

In an embodiment, the disorder diagnosis method may classify the failure diagnosis for the subject by comparing the extracted characteristic data with general fNIRS data or failure criteria data stored in the public database 150 and the failure reference database 160.

Further, embodiments of the present invention include a computer readable medium having program instructions for performing various computer implemented operations. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the media may be those specially designed and constructed for the purposes of the present invention, or they may be of the kind well-known and available to those having skill in the computer software arts. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tape, optical media such as CD-ROMs, DVDs, and magnetic disks, such as floppy disks. Magneto-optical media, and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.

While specific embodiments of the present invention have been described so far, various modifications are possible without departing from the scope of the present invention. Therefore, the scope of the present invention should not be limited to the described embodiments, but should be determined by the equivalents of the claims and the claims.

1 is a diagram showing the configuration of a failure diagnosis apparatus according to an embodiment of the present invention.

2 is a diagram illustrating an example of attaching a transmitter and a receiver to a brain function measurement position according to an embodiment of the present invention.

3 is a diagram illustrating an example of comparing the brain of a general person with a developmental disability according to an embodiment of the present invention.

4 is a flowchart illustrating an example of a failure diagnosis method according to an embodiment of the present invention.

<Explanation of symbols for the main parts of the drawings>

100: fault diagnosis device

110: data collector

120: preprocessing unit

130: feature extraction unit

140: fault diagnosis unit

150: public database

160: failure criteria database

Claims (12)

A public database that stores general FNIRS (FUNCTIONAL NEAR INFRARED SPECTROSCOPY) data; A fault reference database for storing fault reference data; A data collection unit for collecting fNIRS data from a subject; A feature extractor configured to extract feature data using the collected fNIRS data; And The extracted characteristic data is compared with the general fNIRS data and the disability reference data, and when the characteristic data is the same as the general fNIRS data, the characteristic data is not classified as a disability diagnosis, and the characteristic data is the disability reference data. Disability diagnosis unit for classifying the subject as a disability diagnosis, if Failure diagnosis device comprising a. The method of claim 1, The data collection unit, And collecting the fNIRS data through a transmitter and a receiver attached to a location of the brain function of the subject. The method of claim 1, The data collection unit, And a stimulus program used for brain function analysis, wherein the fNIRS data is collected from the subject using any one of a block design protocol, a continuous protocol, and an ERP protocol. The method of claim 1, Pre-processing unit for acquiring the target data by analyzing the collected fNIRS data More, The feature extraction unit, Wavelet (WAVELETS) including Fourier transform theory including Fast Fourier Transform (FFT), Short-time Fourier Transform (STFT), Daubechies, Biorthogonal, and Mexican Hat for the obtained objective data ) Feature, or continuous wavelet transform (CWT) theory to extract the characteristic data using any one of. The method of claim 1, The disorder diagnosis unit, Artificial Neural Network (ANN) theory, Bayesian theory, Hidden Markov-Chain Model (HMM) theory, or Genetic Algorithm (GA) based on the extracted characteristic data, A device for diagnosing a disorder diagnosed by the subject using any one of evolutionary computing theory including an Ant colony system (ACS). The method of claim 1, The disorder diagnosis unit, Disability diagnosis device for classifying the diagnosis of the disorder associated with any one of the cognitive function, language function, social performance function, motor skills function, daily living function for the subject. delete Storing general fNIRS data in a public database; Storing the failure reference data in a failure reference database; Collecting fNIRS data from the subject; Extracting characteristic data using the collected fNIRS data; Comparing the extracted characteristic data with the general fNIRS data and the failure reference data; And As a result of the comparison, if the characteristic data is the same as the general fNIRS data, not classifying the subject as a disorder diagnosis, and if the characteristic data is the same as the disorder reference data, classifying the subject as a disorder diagnosis. Disorder diagnosis method comprising a. The method of claim 8, Collecting the fNIRS data, Collecting fNIRS data from the subject using any one of a block design protocol, a continuous protocol, and an ERP protocol as a stimulus program used for brain function analysis Disorder diagnosis method comprising a. The method of claim 8, Extracting the characteristic data, Signal analyzing the collected fNIRS data to obtain target data; And Fourier transform theory including Fast Fourier Transform (FFT), Short-time Fourier Transform (STFT) on the obtained target data, Wavelet including Daubechies, Biorthogonal, Mexican Hat Extracting characteristic data using either a theory or a continuous wavelet transform (CWT) theory Disorder diagnosis method comprising a. The method of claim 8, Categorizing the diagnosis of the disorder for the subject, Classifying the diagnosis of the disorder related to any one of the cognitive function, the language function, the social function function, the motor function function, and the daily living function for the subject. Disorder diagnosis method comprising a. delete

Images